39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 865329 | 865334 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f8515404180 | 12075203455152141 | 12075203455198412 | 12075203455524809 | 12075203455631712 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 865329 | 865334 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f8515435100 | 12075203470548813 | 12075203470647997 | 12075203470655037 | 12075203470660932 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f8620ffe900 | 0x7f8515435140 | 12075203470694073 | 12075203470706876 | 12075203470837595 | 12075203470841227 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f8620ffe800 | 0x7f8515435180 | 12075203470873176 | 12075203470885915 | 12075203471131193 | 12075203471229508 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f8620ffe700 | 0x7f85154351c0 | 12075203471246931 | 12075203471261272 | 12075203471507669 | 12075203471605667 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f8620ffe600 | 0x7f8515435200 | 12075203471622619 | 12075203471639348 | 12075203471764627 | 12075203471768240 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f8620ffe500 | 0x7f8515435240 | 12075203471783097 | 12075203471794547 | 12075203471920146 | 12075203471923568 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f8620ffe400 | 0x7f8515435280 | 12075203471966418 | 12075203471977745 | 12075203472102224 | 12075203472105246 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f8620ffe300 | 0x7f85154352c0 | 12075203472120093 | 12075203472130864 | 12075203472376622 | 12075203472475263 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f8620ffea00 | 0x7f8515435300 | 12075203472483529 | 12075203472509901 | 12075203472753419 | 12075203472850791 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f8620ffe900 | 0x7f8515435340 | 12075203472859548 | 12075203472885897 | 12075203473011016 | 12075203473014475 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f8620ffe800 | 0x7f8515435380 | 12075203473032319 | 12075203473043816 | 12075203473168615 | 12075203473171948 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f8620ffe700 | 0x7f85154353c0 | 12075203473201072 | 12075203473212135 | 12075203473336454 | 12075203473339700 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f8620ffe600 | 0x7f8515435400 | 12075203473357673 | 12075203473368453 | 12075203473614851 | 12075203473713765 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f8620ffe500 | 0x7f8515435440 | 12075203473722511 | 12075203473751650 | 12075203473995008 | 12075203474065018 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f8620ffe400 | 0x7f8515435480 | 12075203474076499 | 12075203474087807 | 12075203474212126 | 12075203474215768 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f8620ffe300 | 0x7f85154354c0 | 12075203474229554 | 12075203474240286 | 12075203474365245 | 12075203474368752 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f8620ffea00 | 0x7f8515435500 | 12075203474400461 | 12075203474411484 | 12075203474535803 | 12075203474538858 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f8620ffe900 | 0x7f8515435540 | 12075203474553165 | 12075203474563963 | 12075203474816921 | 12075203474861087 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f8620ffe800 | 0x7f8515435580 | 12075203474868782 | 12075203474879960 | 12075203475124758 | 12075203475192974 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f8620ffe700 | 0x7f85154355c0 | 12075203475212070 | 12075203475224597 | 12075203475349876 | 12075203475352981 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f8620ffe600 | 0x7f8515435600 | 12075203475371977 | 12075203475383796 | 12075203475509235 | 12075203475512257 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f8620ffe500 | 0x7f8515435640 | 12075203475539889 | 12075203475550994 | 12075203475675473 | 12075203475678496 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f8620ffe400 | 0x7f8515435680 | 12075203475695939 | 12075203475706833 | 12075203475957871 | 12075203475999603 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f8620ffe300 | 0x7f85154356c0 | 12075203476016114 | 12075203476027150 | 12075203476271308 | 12075203476339825 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f8620ffea00 | 0x7f8515435700 | 12075203476348421 | 12075203476359627 | 12075203476483786 | 12075203476486869 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f8620ffe900 | 0x7f8515435740 | 12075203476511544 | 12075203476522186 | 12075203476647145 | 12075203476650152 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f8620ffe800 | 0x7f8515435780 | 12075203476677092 | 12075203476687944 | 12075203476812263 | 12075203476815349 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f8620ffe700 | 0x7f85154357c0 | 12075203476829495 | 12075203476840423 | 12075203477090501 | 12075203477189985 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f8620ffe600 | 0x7f8515435800 | 12075203477198711 | 12075203477227620 | 12075203477474498 | 12075203477572837 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f8620ffe500 | 0x7f8515435840 | 12075203477581102 | 12075203477609856 | 12075203477734975 | 12075203477738434 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f8620ffe400 | 0x7f8515435880 | 12075203477755105 | 12075203477765855 | 12075203477890974 | 12075203477894334 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f8620ffe300 | 0x7f85154358c0 | 12075203477921024 | 12075203477933534 | 12075203478058652 | 12075203478062366 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f8620ffea00 | 0x7f8515435900 | 12075203478076092 | 12075203478086972 | 12075203478340090 | 12075203478418779 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f8620ffe900 | 0x7f8515435940 | 12075203478427555 | 12075203478458169 | 12075203478706647 | 12075203478755184 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f8620ffe800 | 0x7f8515435980 | 12075203478762818 | 12075203478774806 | 12075203478899605 | 12075203478903029 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f8620ffe700 | 0x7f85154359c0 | 12075203478921683 | 12075203478932245 | 12075203479058164 | 12075203479061443 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f8620ffe600 | 0x7f8515435a00 | 12075203479088093 | 12075203479098963 | 12075203479222962 | 12075203479226179 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f8620ffe500 | 0x7f8515435a40 | 12075203479239915 | 12075203479252242 | 12075203479500240 | 12075203479527259 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f8620ffe400 | 0x7f8515435a80 | 12075203479534843 | 12075203479545840 | 12075203479793357 | 12075203479818169 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f8620ffe300 | 0x7f8515435ac0 | 12075203479826635 | 12075203479838957 | 12075203479963596 | 12075203479966685 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f8620ffea00 | 0x7f8515435b00 | 12075203479980782 | 12075203479992716 | 12075203480119595 | 12075203480122775 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f8620ffe900 | 0x7f8515435b40 | 12075203480149535 | 12075203480161514 | 12075203480286633 | 12075203480289806 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f8620ffe800 | 0x7f8515435b80 | 12075203480303401 | 12075203480316233 | 12075203480580871 | 12075203480607296 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f8620ffe700 | 0x7f8515435bc0 | 12075203480615000 | 12075203480627270 | 12075203480872228 | 12075203480903546 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f8620ffe600 | 0x7f8515435c00 | 12075203480912463 | 12075203480922948 | 12075203481047586 | 12075203481050980 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f8620ffe500 | 0x7f8515435c40 | 12075203481065648 | 12075203481077826 | 12075203481204225 | 12075203481207351 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f8620ffe400 | 0x7f8515435c80 | 12075203481235433 | 12075203481246305 | 12075203481371424 | 12075203481374552 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f8620ffe300 | 0x7f8515435cc0 | 12075203481391834 | 12075203481402463 | 12075203481660861 | 12075203481686922 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f8620ffea00 | 0x7f8515435d00 | 12075203481695328 | 12075203481707741 | 12075203481952219 | 12075203481976230 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f8620ffe900 | 0x7f8515435d40 | 12075203481984084 | 12075203481996378 | 12075203482121017 | 12075203482124125 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f8620ffe800 | 0x7f8515435d80 | 12075203482138331 | 12075203482149977 | 12075203482278296 | 12075203482281397 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f8620ffe700 | 0x7f8515435dc0 | 12075203482309409 | 12075203482321655 | 12075203482447094 | 12075203482450251 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f8620ffe600 | 0x7f8515435e00 | 12075203482467423 | 12075203482479254 | 12075203482738452 | 12075203482760497 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f8620ffe500 | 0x7f8515435e40 | 12075203482770085 | 12075203482782771 | 12075203483032529 | 12075203483062098 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f8620ffe400 | 0x7f8515435e80 | 12075203483070503 | 12075203483082449 | 12075203483207568 | 12075203483210884 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f8620ffe300 | 0x7f8515435ec0 | 12075203483229128 | 12075203483240687 | 12075203483367886 | 12075203483371282 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f8620ffea00 | 0x7f8515435f00 | 12075203483398623 | 12075203483410446 | 12075203483535725 | 12075203483539144 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f8620ffe900 | 0x7f8515435f40 | 12075203483553210 | 12075203483565005 | 12075203483817642 | 12075203483848259 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f8620ffe800 | 0x7f8515435f80 | 12075203483857306 | 12075203483870282 | 12075203484113480 | 12075203484142896 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f8620ffe700 | 0x7f8515435fc0 | 12075203484151232 | 12075203484163559 | 12075203484289158 | 12075203484292564 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f8620ffe600 | 0x7f8515436000 | 12075203484309235 | 12075203484320838 | 12075203484458597 | 12075203484461939 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f8620ffe500 | 0x7f8515436040 | 12075203484488418 | 12075203484500356 | 12075203484625475 | 12075203484628779 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f8620ffe400 | 0x7f8515436080 | 12075203484645881 | 12075203484657475 | 12075203484913793 | 12075203484937924 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f8620ffe300 | 0x7f85154360c0 | 12075203484946239 | 12075203484958592 | 12075203485244030 | 12075203485273557 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f8620ffea00 | 0x7f8515436100 | 12075203485281412 | 12075203485293790 | 12075203485418908 | 12075203485422324 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f8620ffe900 | 0x7f8515436140 | 12075203485435729 | 12075203485448028 | 12075203485590907 | 12075203485594364 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f8620ffe800 | 0x7f8515436180 | 12075203485620993 | 12075203485632987 | 12075203485758106 | 12075203485761655 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f8620ffe700 | 0x7f85154361c0 | 12075203485775470 | 12075203485787225 | 12075203486048823 | 12075203486074265 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f8620ffe600 | 0x7f8515436200 | 12075203486083032 | 12075203486095063 | 12075203486338740 | 12075203486367370 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f8620ffe500 | 0x7f8515436240 | 12075203486375766 | 12075203486387860 | 12075203486513619 | 12075203486517098 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f8620ffe400 | 0x7f8515436280 | 12075203486530453 | 12075203486542259 | 12075203486691537 | 12075203486694979 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f8620ffe300 | 0x7f85154362c0 | 12075203486737809 | 12075203486749457 | 12075203486875056 | 12075203486878440 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f8620ffea00 | 0x7f8515436300 | 12075203486892456 | 12075203486904336 | 12075203487168493 | 12075203487198214 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f8620ffe900 | 0x7f8515436340 | 12075203487206139 | 12075203487218253 | 12075203487462731 | 12075203487490417 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f8620ffe800 | 0x7f8515436380 | 12075203487498332 | 12075203487510730 | 12075203487636489 | 12075203487639665 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f8620ffe700 | 0x7f85154363c0 | 12075203487657217 | 12075203487669129 | 12075203487825768 | 12075203487828936 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f8620ffe600 | 0x7f8515436400 | 12075203487855476 | 12075203487867367 | 12075203487992486 | 12075203487995977 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f8620ffe500 | 0x7f8515436440 | 12075203488012578 | 12075203488024326 | 12075203488278404 | 12075203488301935 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f8620ffe400 | 0x7f8515436480 | 12075203488309950 | 12075203488321923 | 12075203488570561 | 12075203488594018 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f8620ffe300 | 0x7f85154364c0 | 12075203488602574 | 12075203488614401 | 12075203488740160 | 12075203488743576 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f8620ffea00 | 0x7f8515436500 | 12075203488757432 | 12075203488767999 | 12075203488932798 | 12075203488936244 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f8620ffe900 | 0x7f8515436540 | 12075203488962373 | 12075203488972958 | 12075203489140316 | 12075203489143509 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f8620ffe800 | 0x7f8515436580 | 12075203489157756 | 12075203489168316 | 12075203489432154 | 12075203489457583 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f8620ffe700 | 0x7f85154365c0 | 12075203489465878 | 12075203489477273 | 12075203489722711 | 12075203489742472 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f8620ffe600 | 0x7f8515436600 | 12075203489755126 | 12075203489765751 | 12075203489892470 | 12075203489895958 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f8620ffe500 | 0x7f8515436640 | 12075203489910004 | 12075203489921909 | 12075203490094068 | 12075203490097662 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f8620ffe400 | 0x7f8515436680 | 12075203490125674 | 12075203490137587 | 12075203490262706 | 12075203490266166 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f8620ffe300 | 0x7f85154366c0 | 12075203490280051 | 12075203490291506 | 12075203490545424 | 12075203490569339 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f8620ffea00 | 0x7f8515436700 | 12075203490577614 | 12075203490587824 | 12075203490832781 | 12075203490856092 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f8620ffe900 | 0x7f8515436740 | 12075203490864187 | 12075203490876141 | 12075203491002220 | 12075203491005429 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f8620ffe800 | 0x7f8515436780 | 12075203491019075 | 12075203491031180 | 12075203491213738 | 12075203491217223 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f8620ffe700 | 0x7f85154367c0 | 12075203491245335 | 12075203491256138 | 12075203491381897 | 12075203491385295 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f8620ffe600 | 0x7f8515436800 | 12075203491398810 | 12075203491409736 | 12075203491673254 | 12075203491697776 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f8620ffe500 | 0x7f8515436840 | 12075203491706021 | 12075203491718054 | 12075203491964132 | 12075203491988987 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f8620ffe400 | 0x7f8515436880 | 12075203491996571 | 12075203492011811 | 12075203492138210 | 12075203492141751 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f8620ffe300 | 0x7f85154368c0 | 12075203492156218 | 12075203492167010 | 12075203492358048 | 12075203492362141 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f8620ffea00 | 0x7f8515436900 | 12075203492389181 | 12075203492401248 | 12075203492527327 | 12075203492530824 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f8620ffe900 | 0x7f8515436940 | 12075203492544540 | 12075203492556286 | 12075203492837884 | 12075203492862721 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f8620ffe800 | 0x7f8515436980 | 12075203492870876 | 12075203492882844 | 12075203493131641 | 12075203493158621 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f8620ffe700 | 0x7f85154369c0 | 12075203493167006 | 12075203493177721 | 12075203493303000 | 12075203493306265 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f8620ffe600 | 0x7f8515436a00 | 12075203493320762 | 12075203493331480 | 12075203493541078 | 12075203493567310 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f8620ffe500 | 0x7f8515436a40 | 12075203493588930 | 12075203493601557 | 12075203493729716 | 12075203493732978 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f8620ffe400 | 0x7f8515436a80 | 12075203493750641 | 12075203493761236 | 12075203494068113 | 12075203494093739 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f8620ffe300 | 0x7f8515436ac0 | 12075203494105611 | 12075203494117553 | 12075203494365231 | 12075203494388266 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f8620ffea00 | 0x7f8515436b00 | 12075203494396191 | 12075203494407950 | 12075203494535309 | 12075203494538675 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f8620ffe900 | 0x7f8515436b40 | 12075203494552942 | 12075203494564269 | 12075203494792267 | 12075203494815470 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f8620ffe800 | 0x7f8515436b80 | 12075203494837771 | 12075203494849706 | 12075203494976745 | 12075203494980046 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f8620ffe700 | 0x7f8515436bc0 | 12075203494993701 | 12075203495005385 | 12075203495333862 | 12075203495358399 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f8620ffe600 | 0x7f8515436c00 | 12075203495366394 | 12075203495378342 | 12075203495626660 | 12075203495649921 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f8620ffe500 | 0x7f8515436c40 | 12075203495658607 | 12075203495670499 | 12075203495799138 | 12075203495802424 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f8620ffe400 | 0x7f8515436c80 | 12075203495816410 | 12075203495828098 | 12075203496072416 | 12075203496096821 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f8620ffe300 | 0x7f8515436cc0 | 12075203496118982 | 12075203496130815 | 12075203496260094 | 12075203496263481 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f8620ffea00 | 0x7f8515436d00 | 12075203496277066 | 12075203496288894 | 12075203496663611 | 12075203496686567 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f8620ffe900 | 0x7f8515436d40 | 12075203496694943 | 12075203496706810 | 12075203496959448 | 12075203496982868 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f8620ffe800 | 0x7f8515436d80 | 12075203496991213 | 12075203497002968 | 12075203497132247 | 12075203497135642 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f8620ffe700 | 0x7f8515436dc0 | 12075203497149537 | 12075203497163766 | 12075203497441684 | 12075203497466797 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f8620ffe600 | 0x7f8515436e00 | 12075203497488668 | 12075203497499283 | 12075203497633042 | 12075203497636613 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f8620ffe500 | 0x7f8515436e40 | 12075203497653824 | 12075203497665682 | 12075203498089038 | 12075203498117546 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f8620ffe400 | 0x7f8515436e80 | 12075203498126613 | 12075203498137198 | 12075203498407916 | 12075203498435387 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f8620ffe300 | 0x7f8515436ec0 | 12075203498443823 | 12075203498455755 | 12075203498590954 | 12075203498594463 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f8620ffea00 | 0x7f8515436f00 | 12075203498608148 | 12075203498620714 | 12075203498935111 | 12075203498959311 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f8620ffe900 | 0x7f8515436f40 | 12075203498981872 | 12075203498993990 | 12075203499144709 | 12075203499148512 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f8620ffe800 | 0x7f8515436f80 | 12075203499162508 | 12075203499173989 | 12075203499689664 | 12075203499716798 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f8620ffe700 | 0x7f8515436fc0 | 12075203499725975 | 12075203499737824 | 12075203500035901 | 12075203500064194 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f8620ffe600 | 0x7f8515437000 | 12075203500072980 | 12075203500085021 | 12075203500239580 | 12075203500243227 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f8620ffe500 | 0x7f8515437040 | 12075203500257162 | 12075203500267579 | 12075203500652696 | 12075203500679758 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f8620ffe400 | 0x7f8515437080 | 12075203500702210 | 12075203500712855 | 12075203500889014 | 12075203500892603 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f8620ffe300 | 0x7f85154370c0 | 12075203500906209 | 12075203500918454 | 12075203501527408 | 12075203501560705 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f8620ffea00 | 0x7f8515437100 | 12075203501570984 | 12075203501583088 | 12075203501909165 | 12075203501936453 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f8620ffe900 | 0x7f8515437140 | 12075203501949327 | 12075203501959885 | 12075203502137803 | 12075203502141484 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f8620ffe800 | 0x7f8515437180 | 12075203502158776 | 12075203502170603 | 12075203502625799 | 12075203502653365 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f8620ffe700 | 0x7f85154371c0 | 12075203502674455 | 12075203502686278 | 12075203502884837 | 12075203502911756 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f8620ffe600 | 0x7f8515437200 | 12075203502919059 | 12075203502932836 | 12075203503635710 | 12075203503663893 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f8620ffe500 | 0x7f8515437240 | 12075203503672750 | 12075203503684510 | 12075203504057306 | 12075203504086579 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f8620ffe400 | 0x7f8515437280 | 12075203504094874 | 12075203504107066 | 12075203504309304 | 12075203504339248 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f8620ffe300 | 0x7f85154372c0 | 12075203504347093 | 12075203504359064 | 12075203504884179 | 12075203504912444 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f8620ffea00 | 0x7f8515437300 | 12075203504936218 | 12075203504948339 | 12075203505171377 | 12075203505206480 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f8620ffe900 | 0x7f8515437340 | 12075203505215647 | 12075203505226256 | 12075203506024169 | 12075203506053554 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f8620ffe800 | 0x7f8515437380 | 12075203506062381 | 12075203506073129 | 12075203506493605 | 12075203506520672 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f8620ffe700 | 0x7f85154373c0 | 12075203506529378 | 12075203506540005 | 12075203506764323 | 12075203506787198 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f8620ffe600 | 0x7f8515437400 | 12075203506799390 | 12075203506811362 | 12075203507407357 | 12075203507434721 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f8620ffe500 | 0x7f8515437440 | 12075203507457193 | 12075203507468957 | 12075203507737594 | 12075203507765315 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f8620ffe400 | 0x7f8515437480 | 12075203507773230 | 12075203507783674 | 12075203508767665 | 12075203508802683 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f8620ffe300 | 0x7f85154374c0 | 12075203508810768 | 12075203508820785 | 12075203509352140 | 12075203509386017 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f8620ffea00 | 0x7f8515437500 | 12075203509395144 | 12075203509407180 | 12075203509677578 | 12075203509704980 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f8620ffe900 | 0x7f8515437540 | 12075203509714387 | 12075203509726697 | 12075203510463491 | 12075203510492554 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f8620ffe800 | 0x7f8515437580 | 12075203510514675 | 12075203510526530 | 12075203510840607 | 12075203510867851 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f8620ffe700 | 0x7f85154375c0 | 12075203510876657 | 12075203510888287 | 12075203512058997 | 12075203512090363 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f8620ffe600 | 0x7f8515437600 | 12075203512099029 | 12075203512110996 | 12075203512721551 | 12075203512748686 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f8620ffe500 | 0x7f8515437640 | 12075203512757402 | 12075203512769391 | 12075203513087948 | 12075203513118113 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f8620ffe400 | 0x7f8515437680 | 12075203513130396 | 12075203513142347 | 12075203514020420 | 12075203514050405 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f8620ffe300 | 0x7f85154376c0 | 12075203514073288 | 12075203514085219 | 12075203514494496 | 12075203514523274 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f8620ffea00 | 0x7f8515437700 | 12075203514531680 | 12075203514543775 | 12075203516093042 | 12075203516164133 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f8620ffe900 | 0x7f8515437740 | 12075203516175595 | 12075203516187441 | 12075203516981674 | 12075203517052394 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f8620ffe800 | 0x7f8515437780 | 12075203517061371 | 12075203517071913 | 12075203517485350 | 12075203517555800 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f8620ffe700 | 0x7f85154377c0 | 12075203517564616 | 12075203517575665 | 12075203518733736 | 12075203518808437 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f8620ffe600 | 0x7f8515437800 | 12075203518830769 | 12075203518843334 | 12075203519628448 | 12075203519703280 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f8620ffe500 | 0x7f8515437840 | 12075203519714421 | 12075203519725568 | 12075203522775465 | 12075203522846231 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f8620ffe400 | 0x7f8515437880 | 12075203522854767 | 12075203522866505 | 12075203524406173 | 12075203524481480 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f8620ffe300 | 0x7f85154378c0 | 12075203524491489 | 12075203524504252 | 12075203525293047 | 12075203525362377 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f8620ffea00 | 0x7f8515437900 | 12075203525376614 | 12075203525389046 | 12075203527669669 | 12075203527739465 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f8620ffe900 | 0x7f8515437940 | 12075203527762808 | 12075203527775108 | 12075203529309497 | 12075203529379502 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f8620ffe800 | 0x7f8515437980 | 12075203529388599 | 12075203529399736 | 12075203535453612 | 12075203535523671 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f8620ffe700 | 0x7f85154379c0 | 12075203535532627 | 12075203535544811 | 12075203538585909 | 12075203538656322 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f8620ffe600 | 0x7f8515437a00 | 12075203538665589 | 12075203538678068 | 12075203540215977 | 12075203540286261 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 865329 | 865334 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f8620ffe500 | 0x7f8515437a40 | 12075203540296130 | 12075203540308936 | 12075203544835143 | 12075203544905435 |